Skip to content

This repo is a packaged version of the Yolov6 model.

License

Notifications You must be signed in to change notification settings

kadirnar/yolov6-pip

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

26 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Yolov6-Pip: Packaged version of the Yolov6 repository

teaser

downloads pypi version HuggingFace Spaces

Overview

This repo is a packaged version of the Yolov6 model.

Benchmark

Model Size mAPval
0.5:0.95
SpeedT4
trt fp16 b1
(fps)
SpeedT4
trt fp16 b32
(fps)
Params
(M)
FLOPs
(G)
YOLOv6-N 640 37.5 779 1187 4.7 11.4
YOLOv6-S 640 45.0 339 484 18.5 45.3
YOLOv6-M 640 50.0 175 226 34.9 85.8
YOLOv6-L 640 52.8 98 116 59.6 150.7
YOLOv6-N6 1280 44.9 228 281 10.4 49.8
YOLOv6-S6 1280 50.3 98 108 41.4 198.0
YOLOv6-M6 1280 55.2 47 55 79.6 379.5
YOLOv6-L6 1280 57.2 26 29 140.4 673.4

Installation

pip install yolov6detect

Yolov6 Inference

from yolov6 import YOLOV6

model = YOLOV6(weights='yolov6s.pt', device='cuda:0') 
#model = YOLOV6(weights='kadirnar/yolov6t-v2.0', device='cuda:0', hf_model=True)

model.classes = None
model.conf = 0.25
model.iou_ = 0.45
model.show = False
model.save = True

pred = model.predict(source='data/images',yaml='data/coco.yaml', img_size=640)

Citation

@article{li2022yolov6,
  title={YOLOv6: A single-stage object detection framework for industrial applications},
  author={Li, Chuyi and Li, Lulu and Jiang, Hongliang and Weng, Kaiheng and Geng, Yifei and Li, Liang and Ke, Zaidan and Li, Qingyuan and Cheng, Meng and Nie, Weiqiang and others},
  journal={arXiv preprint arXiv:2209.02976},
  year={2022}
}